Machine learning for automated 3-dimensional segmentation of the spine and suggested placement of pedicle screws based on intraoperative cone-beam computer tomography

Burström, Gustav; Buerger, Christian; Hoppenbrouwers, J. J. L.; Nachabé, Rami; Lorenz, Cristian; Babić, Draženko; Homan, Robert; Racadio, John M.; Graß, Michael; Persson, Oscar; Edström, Erik; Elmi-Terander, Adrian

doi:10.3171/2018.12.spine181397

Cited by 56 publications

(59 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pedicle screw paths were planned using an augmented reality surgical navigation (ARSN) system, as previously described in the literature [23]. Accordingly, a cone beam computed tomography (CBCT) acquisition was performed and used for automatic spine segmentation and creation of a 3D-model of the spine [24]. Based on this 3D-model, using the system's surgical navigation software, pedicle screws were purposefully planned to result in either lateral, inferior, anterior, or medial breach.…”

Section: Surgical Setupmentioning

confidence: 99%

Diffuse reflectance spectroscopy accurately identifies the pre-cortical zone to avoid impending pedicle screw breach in spinal fixation surgery

Burström

Swamy

Spliethoff

et al. 2019

Biomed. Opt. Express

Self Cite

View full text Add to dashboard Cite

Pedicle screw placement accuracy during spinal fixation surgery varies greatly and severe misplacement has been reported in 1-6.5 % of screws. Diffuse reflectance (DR) spectroscopy has previously been shown to reliably discriminate between tissues in the human body. We postulate that it could be used to discriminate between cancellous and cortical bone. Therefore, the purpose of this study is to validate DR spectroscopy as a warning system to detect impending pedicle screw breach in a cadaveric surgical setting using typical clinical breach scenarios. DR spectroscopy was incorporated at the tip of an integrated pedicle screw and screw driver used for tissue probing during pedicle screw insertions on six cadavers. Measurements were collected in the wavelength range of 400-1600 nm and each insertion was planned to result in a breach. Measurements were labelled as cancellous, cortical or representing a pre-cortical zone (PCZ) in between, based on information from cone beam computed tomographies at corresponding positions. In addition, DR spectroscopy data was recorded after breach. Four typical pedicle breach types were performed, and a total of 45 pedicle breaches were recorded. For each breach direction, the technology was able to detect the transition of the screw tip from the cancellous bone to the PCZ (P < 0.001), to cortical bone (P < 0.001), and to a subsequent breach (P < 0.001). Using support vector machine (SVM) classification, breach could reliably be detected with a sensitivity of 98.3 % [94.3-100 %] and a specificity of 97.7 % [91.0-100 %]. We conclude that DR spectroscopy reliably identifies the area of transition from cancellous to cortical bone in typical breach scenarios and can warn the surgeon of impending pedicle breach, thereby resulting in safer spinal fixation surgeries.

show abstract

Section: Surgical Setupmentioning

confidence: 99%

Diffuse reflectance spectroscopy accurately identifies the pre-cortical zone to avoid impending pedicle screw breach in spinal fixation surgery

Burström

Swamy

Spliethoff

et al. 2019

Biomed. Opt. Express

Self Cite

View full text Add to dashboard Cite

show abstract

“…Image fusion on endoscopic views for endonasal skull-base surgery Using augmented reality for surgical navigation has several potential benefits compared to conventional navigation with display of 2D medical imaging on a separate screen. Overlaying segmented anatomical structures from CT or MRI on the endoscopic video stream enables navigation without the use of dedicated instruments and thereby improves workflow, while visualizing sub-surface anatomy [48]. However, it has been shown that although users of AR navigation were able to identify a target more accurately, they were at the same time at risk of inattentional blindness, e.g.…”

Section: Discussionmentioning

confidence: 99%

“…to evaluate tumor resection grade or intraoperative changes of anatomy. Fast and accurate segmentation of CBCT images has been performed successfully intraoperatively in the system's spine surgery application [48].…”

Section: Discussionmentioning

confidence: 99%

Fusion of augmented reality imaging with the endoscopic view for endonasal skull base surgery; a novel application for surgical navigation based on intraoperative cone beam computed tomography and optical tracking

et al. 2020

Self Cite

View full text Add to dashboard Cite

ObjectiveSurgical navigation is a well-established tool in endoscopic skull base surgery. However, navigational and endoscopic views are usually displayed on separate monitors, forcing the surgeon to focus on one or the other. Aiming to provide real-time integration of endoscopic and diagnostic imaging information, we present a new navigation technique based on augmented reality with fusion of intraoperative cone beam computed tomography (CBCT) on the endoscopic view. The aim of this study was to evaluate the accuracy of the method. Material and methodsAn augmented reality surgical navigation system (ARSN) with 3D CBCT capability was used. The navigation system incorporates an optical tracking system (OTS) with four video cameras embedded in the flat detector of the motorized C-arm. Intra-operative CBCT images were fused with the view of the surgical field obtained by the endoscope's camera. Accuracy of CBCT image co-registration was tested using a custom-made grid with incorporated 3D spheres.

show abstract

“…After exposure of the spine, adhesive skin markers were placed for patient tracking and a 3D cone beam CT (CBCT) was performed to image the region that required spinal instrumentation. Planning of pedicle screw trajectories was performed based on the CBCT images and automatic spine segmentation 10 . The screws were one by one activated in the software.…”

Section: Methodsmentioning

confidence: 99%

Augmented reality navigation with intraoperative 3D imaging vs fluoroscopy-assisted free-hand surgery for spine fixation surgery: a matched-control study comparing accuracy

Elmi-Terander

Burström

Nachabé

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

This study aimed to compare screw placement accuracy and clinical aspects between Augmented Reality Surgical Navigation (ARSN) and free-hand (FH) technique. Twenty patients underwent spine surgery with screw placement using ARSN and were matched retrospectively to a cohort of 20 FH technique cases for comparison. All ARSN and FH cases were performed by the same surgeon. Matching was based on clinical diagnosis and similar proportions of screws placed in the thoracic and lumbosacral vertebrae in both groups. Accuracy of screw placement was assessed on postoperative scans according to the Gertzbein scale and grades 0 and 1 were considered accurate. Procedure time, blood loss and length of hospital stay, were collected as secondary endpoints. A total of 262 and 288 screws were assessed in the ARSN and FH groups, respectively. The share of clinically accurate screws was significantly higher in the ARSN vs FH group (93.9% vs 89.6%, p < 0.05). The proportion of screws placed without a cortical breach was twice as high in the ARSN group compared to the FH group (63.4% vs 30.6%, p < 0.0001). No statistical difference was observed for the secondary endpoints between both groups. This matched-control study demonstrated that ARSN provided higher screw placement accuracy compared to free-hand.Compared to conventional free-hand (FH) surgical technique, computer-assisted navigation using intraoperative 3D imaging has been shown to improve screw placement accuracy and reduce complications due to screw misplacements 1 . Moreover, improved accuracy has also been shown in more challenging conditions, such as scoliosis surgery, where it may be of even greater importance 2 . Consequently, navigation also reduces the frequency of postoperative revision surgery compared to FH surgery 3 .Although several studies have compared intraoperative image guidance to free-hand (FH) technique, the evidence in favor of navigation is still limited. In a recent systematic review, Chan et al., found only four studies comparing computed tomography (CT) guidance with free-hand methods head-to-head, including one small (10 patients in each group, 169 screws in total) randomized study 4 . Overall, the reviewers found only moderate level evidence showing that CT guidance has lower breach rates than FH, while screw-related complication rates were conflicting at 0% in CT navigation compared with 0%-1.7% in FH groups 5 . In a more recent retrospective study comparing O-arm navigation to FH, Wang et al. demonstrated higher pedicle screw accuracy and lower total

show abstract

Machine learning for automated 3-dimensional segmentation of the spine and suggested placement of pedicle screws based on intraoperative cone-beam computer tomography

Cited by 56 publications

References 31 publications

Diffuse reflectance spectroscopy accurately identifies the pre-cortical zone to avoid impending pedicle screw breach in spinal fixation surgery

Diffuse reflectance spectroscopy accurately identifies the pre-cortical zone to avoid impending pedicle screw breach in spinal fixation surgery

Fusion of augmented reality imaging with the endoscopic view for endonasal skull base surgery; a novel application for surgical navigation based on intraoperative cone beam computed tomography and optical tracking

Augmented reality navigation with intraoperative 3D imaging vs fluoroscopy-assisted free-hand surgery for spine fixation surgery: a matched-control study comparing accuracy

Contact Info

Product

Resources

About